| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.19455252918287938, | |
| "eval_steps": 9, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.007782101167315175, | |
| "grad_norm": 0.15050330758094788, | |
| "learning_rate": 1e-05, | |
| "loss": 10.3688, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.007782101167315175, | |
| "eval_loss": NaN, | |
| "eval_runtime": 0.3507, | |
| "eval_samples_per_second": 307.972, | |
| "eval_steps_per_second": 39.922, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.01556420233463035, | |
| "grad_norm": 0.2052978277206421, | |
| "learning_rate": 2e-05, | |
| "loss": 10.3736, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.023346303501945526, | |
| "grad_norm": 0.22770772874355316, | |
| "learning_rate": 3e-05, | |
| "loss": 10.3135, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0311284046692607, | |
| "grad_norm": 0.20140793919563293, | |
| "learning_rate": 4e-05, | |
| "loss": 10.2939, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.038910505836575876, | |
| "grad_norm": 0.19401751458644867, | |
| "learning_rate": 5e-05, | |
| "loss": 10.3256, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.04669260700389105, | |
| "grad_norm": 0.18698450922966003, | |
| "learning_rate": 6e-05, | |
| "loss": 10.3705, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.054474708171206226, | |
| "grad_norm": 0.27336716651916504, | |
| "learning_rate": 7e-05, | |
| "loss": 10.3191, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0622568093385214, | |
| "grad_norm": 0.22764867544174194, | |
| "learning_rate": 8e-05, | |
| "loss": 10.3599, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.07003891050583658, | |
| "grad_norm": 0.21836555004119873, | |
| "learning_rate": 9e-05, | |
| "loss": 10.3509, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.07003891050583658, | |
| "eval_loss": NaN, | |
| "eval_runtime": 0.3723, | |
| "eval_samples_per_second": 290.06, | |
| "eval_steps_per_second": 37.6, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.07782101167315175, | |
| "grad_norm": 0.09972412884235382, | |
| "learning_rate": 0.0001, | |
| "loss": 10.3629, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.08560311284046693, | |
| "grad_norm": 0.1307542771100998, | |
| "learning_rate": 9.99695413509548e-05, | |
| "loss": 10.3581, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0933852140077821, | |
| "grad_norm": 0.21208789944648743, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 10.3348, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.10116731517509728, | |
| "grad_norm": 0.22375652194023132, | |
| "learning_rate": 9.972609476841367e-05, | |
| "loss": 10.3007, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.10894941634241245, | |
| "grad_norm": 0.2047107070684433, | |
| "learning_rate": 9.951340343707852e-05, | |
| "loss": 10.32, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.11673151750972763, | |
| "grad_norm": 0.16958235204219818, | |
| "learning_rate": 9.924038765061042e-05, | |
| "loss": 10.3279, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.1245136186770428, | |
| "grad_norm": 0.26593777537345886, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 10.3441, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.13229571984435798, | |
| "grad_norm": 0.3536827862262726, | |
| "learning_rate": 9.851478631379982e-05, | |
| "loss": 10.3664, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.14007782101167315, | |
| "grad_norm": 0.38606491684913635, | |
| "learning_rate": 9.806308479691595e-05, | |
| "loss": 10.2935, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.14007782101167315, | |
| "eval_loss": NaN, | |
| "eval_runtime": 0.3716, | |
| "eval_samples_per_second": 290.664, | |
| "eval_steps_per_second": 37.679, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.14785992217898833, | |
| "grad_norm": 0.0, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.1556420233463035, | |
| "grad_norm": 0.0, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.16342412451361868, | |
| "grad_norm": 0.3168112635612488, | |
| "learning_rate": 9.635919272833938e-05, | |
| "loss": 10.3187, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.17120622568093385, | |
| "grad_norm": 0.0, | |
| "learning_rate": 9.567727288213005e-05, | |
| "loss": 0.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.17898832684824903, | |
| "grad_norm": 0.2514454126358032, | |
| "learning_rate": 9.493970231495835e-05, | |
| "loss": 10.3512, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.1867704280155642, | |
| "grad_norm": 0.0, | |
| "learning_rate": 9.414737964294636e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.19455252918287938, | |
| "grad_norm": 0.21714404225349426, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 10.3402, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 100, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1909039300608.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |